… heuristics for topic-aware influence maximization (TIM) problems. The point of our approach
is the combination of deep graph embedding with reinforcement learning. Besides, we …

… by leveraging deep reinforcement learning (RL) to estimate the expected influence. In …
a novel framework called deeP reInforcement leArning-based iNfluence maximizatiOn (PIANO) …

… In this article, we have modeled the influence maximization of complex networks as the … of
a deep Q network, and have proposed an evolutionary deep reinforcement learning algorithm (…

… influence on networks, the influence maximization (IM) problem has been extensively studied.
Since it is #P-hard to compute the influence … achievements of deep reinforcement learning (…

… method that efficiently solves the problem of balanced influence maximization in multi-entity …
a Balanced Influence Maximization framework based on Deep Reinforcement Learning …

… challenges, we integrate deep reinforcement learning [6], [7] … further acts as input to deep
reinforcement learning. For the … ; Θ) using a deep reinforcement learning technique. For each …

… learning models to address the competitive influence maximization (CIM) problem. … a deep
reinforcement learning-based (DRL) model to tackle the competitive influence maximization …

… of a node v can be very complex and may depend on complicated statistics such as
global/local degree distribution, distance to tagged nodes in these problems, we will use a deep …

… Reinforcement Learning for Influence Maximization (RL4IM), a new RL-based algorithm
that addresses the contingency-aware IM problem. RL4IM exploits two significant properties in …

… Therefore, we employ reinforcement learning by converting the problem into a Markov …
Since we use deep reinforcement learning methods that require the states and actions to be …